Efficient Symmetry-Aware Materials Generation via Hierarchical Generative Flow Networks
- URL: http://arxiv.org/abs/2411.04323v1
- Date: Wed, 06 Nov 2024 23:53:34 GMT
- Title: Efficient Symmetry-Aware Materials Generation via Hierarchical Generative Flow Networks
- Authors: Tri Minh Nguyen, Sherif Abdulkader Tawfik, Truyen Tran, Sunil Gupta, Santu Rana, Svetha Venkatesh,
- Abstract summary: New solid-state materials require rapidly exploring the vast space of crystal structures and locating stable regions.
Existing methods struggle to explore large material spaces and generate diverse samples with desired properties and requirements.
We propose a novel generative model employing a hierarchical exploration strategy to efficiently exploit the symmetry of the materials space to generate crystal structures given desired properties.
- Score: 52.13486402193811
- License:
- Abstract: Discovering new solid-state materials requires rapidly exploring the vast space of crystal structures and locating stable regions. Generating stable materials with desired properties and compositions is extremely difficult as we search for very small isolated pockets in the exponentially many possibilities, considering elements from the periodic table and their 3D arrangements in crystal lattices. Materials discovery necessitates both optimized solution structures and diversity in the generated material structures. Existing methods struggle to explore large material spaces and generate diverse samples with desired properties and requirements. We propose the Symmetry-aware Hierarchical Architecture for Flow-based Traversal (SHAFT), a novel generative model employing a hierarchical exploration strategy to efficiently exploit the symmetry of the materials space to generate crystal structures given desired properties. In particular, our model decomposes the exponentially large materials space into a hierarchy of subspaces consisting of symmetric space groups, lattice parameters, and atoms. We demonstrate that SHAFT significantly outperforms state-of-the-art iterative generative methods, such as Generative Flow Networks (GFlowNets) and Crystal Diffusion Variational AutoEncoders (CDVAE), in crystal structure generation tasks, achieving higher validity, diversity, and stability of generated structures optimized for target properties and requirements.
Related papers
- Symmetry-Aware Bayesian Flow Networks for Crystal Generation [0.562479170374811]
We introduce SymmBFN, a novel symmetry-aware Bayesian Flow Network (BFN) for crystalline material generation.
SymmBFN substantially improves efficiency, generating stable structures at least 50 times faster than the next-best method.
Our findings establish BFNs as an effective tool for accelerating the discovery of crystalline materials.
arXiv Detail & Related papers (2025-02-05T13:14:50Z) - Open Materials Generation with Stochastic Interpolants [14.939468363546384]
We introduce Open Materials Generation (OMG), a unifying framework for the generative design and discovery of crystalline materials.
OMG employs inorganic interpolants (SI) to bridge an arbitrary base distribution to the target distribution of crystals.
We benchmark OMG's performance on two tasks: Crystal Structure Prediction (CSP) for specified compositions, and 'de novo' generation (DNG) aimed at discovering stable, novel, and unique structures.
arXiv Detail & Related papers (2025-02-04T18:56:47Z) - MIND: Microstructure INverse Design with Generative Hybrid Neural Representation [25.55691106041371]
inverse design of microstructures plays a pivotal role in optimizing metamaterials with specific, targeted physical properties.
We present a novel generative model that integrates latent diffusion with Holoplane, an advanced hybrid neural representation that simultaneously encodes both geometric and physical properties.
Our approach generalizes across multiple microstructure classes, enabling the generation of diverse, tileable microstructures with significantly improved property accuracy and enhanced control over geometric validity.
arXiv Detail & Related papers (2025-02-01T20:25:47Z) - Unleashing the power of novel conditional generative approaches for new materials discovery [3.972733741872872]
We propose two generative approaches to the problem of crystal structure design.
One is conditional structure modification, using the energy difference between the most energetically favorable structure and all its less stable polymorphs.
The other is conditional structure generation, using the energy difference between the most energetically favorable structure and all its less stable polymorphs.
arXiv Detail & Related papers (2024-11-05T14:58:31Z) - Generative Hierarchical Materials Search [91.93125016916463]
We propose Generative Hierarchical Materials Search (GenMS) for controllable generation of crystal structures.
GenMS consists of (1) a language model that takes high-level natural language as input and generates intermediate textual information about a crystal.
GenMS additionally uses a graph neural network to predict properties (e.g., formation energy) from the generated crystal structures.
arXiv Detail & Related papers (2024-09-10T17:51:28Z) - DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization [49.85944390503957]
DecompOpt is a structure-based molecular optimization method based on a controllable and diffusion model.
We show that DecompOpt can efficiently generate molecules with improved properties than strong de novo baselines.
arXiv Detail & Related papers (2024-03-07T02:53:40Z) - Scalable Diffusion for Materials Generation [99.71001883652211]
We develop a unified crystal representation that can represent any crystal structure (UniMat)
UniMat can generate high fidelity crystal structures from larger and more complex chemical systems.
We propose additional metrics for evaluating generative models of materials.
arXiv Detail & Related papers (2023-10-18T15:49:39Z) - Crystal-GFN: sampling crystals with desirable properties and constraints [103.79058968784163]
We introduce Crystal-GFN, a generative model of crystal structures that sequentially samples structural properties of crystalline materials.
In this paper, we use as objective the formation energy per atom of a crystal structure predicted by a new proxy machine learning model trained on MatBench.
The results demonstrate that Crystal-GFN is able to sample highly diverse crystals with low (median -3.1 eV/atom) predicted formation energy.
arXiv Detail & Related papers (2023-10-07T21:36:55Z) - How to See Hidden Patterns in Metamaterials with Interpretable Machine
Learning [82.67551367327634]
We develop a new interpretable, multi-resolution machine learning framework for finding patterns in the unit-cells of materials.
Specifically, we propose two new interpretable representations of metamaterials, called shape-frequency features and unit-cell templates.
arXiv Detail & Related papers (2021-11-10T21:19:02Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.